CN116527084B - Filtering method, system, equipment and medium for power line communication carrier - Google Patents
Filtering method, system, equipment and medium for power line communication carrier Download PDFInfo
- Publication number
- CN116527084B CN116527084B CN202310814914.0A CN202310814914A CN116527084B CN 116527084 B CN116527084 B CN 116527084B CN 202310814914 A CN202310814914 A CN 202310814914A CN 116527084 B CN116527084 B CN 116527084B
- Authority
- CN
- China
- Prior art keywords
- filtering
- data
- score
- preset
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 394
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004891 communication Methods 0.000 title claims abstract description 36
- 238000003062 neural network model Methods 0.000 claims abstract description 44
- 238000012549 training Methods 0.000 claims description 44
- 238000012360 testing method Methods 0.000 claims description 41
- 230000006870 function Effects 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B3/00—Line transmission systems
- H04B3/54—Systems for transmission via power distribution lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/148—Wavelet transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03H—IMPEDANCE NETWORKS, e.g. RESONANT CIRCUITS; RESONATORS
- H03H17/00—Networks using digital techniques
- H03H17/02—Frequency selective networks
- H03H17/0248—Filters characterised by a particular frequency response or filtering method
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03H—IMPEDANCE NETWORKS, e.g. RESONANT CIRCUITS; RESONATORS
- H03H2222/00—Indexing scheme relating to digital filtering methods
- H03H2222/04—Indexing scheme relating to digital filtering methods using neural networks
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03H—IMPEDANCE NETWORKS, e.g. RESONANT CIRCUITS; RESONATORS
- H03H2222/00—Indexing scheme relating to digital filtering methods
- H03H2222/06—Indexing scheme relating to digital filtering methods using wavelets
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Computational Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a filtering method, a system, equipment and a medium of a power line communication carrier, which are used for responding to a received signal filtering request, determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal, filtering operation is carried out by adopting the first original signal, determining a first filtering value corresponding to the first filtering data, a second filtering value corresponding to the second filtering data is determined by adopting a second original signal to input a preset filtering neural network model, the first filtering value and the second filtering value are compared, if the first filtering value is larger than the second filtering value, the first filtering data is output, and if the first filtering value is smaller than or equal to the second filtering value, the second filtering data is output; the method solves the technical problem that the existing PLC filtering scheme mostly adopts a single filter scheme, and high-quality filtering cannot be obtained in a complex interference environment.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method, a system, an apparatus, and a medium for filtering a power line communication carrier.
Background
Power line communication technology refers to a communication scheme that utilizes a power line to transmit data and media signals. The power line communication technology is to load high frequency carrying information to current and then to use an adapter for transmitting and receiving information by using wires to separate the high frequency from the current and transmit the high frequency to a computer or a telephone so as to realize information transmission. Compared with various wired communication technologies, the method has the advantages of no need of rewiring, easiness in networking and the like, and has a wide application prospect.
In practical application, the existing carrier transmission distance is short, interference is large, data recovery rate is low, bandwidth is small, and most of the existing PLC filtering schemes adopt a single filter scheme, so that the problem that high-quality filtering cannot be obtained in a complex interference environment exists.
Disclosure of Invention
The invention provides a filtering method, a system, equipment and a medium of a power line communication carrier wave, which solve the technical problem that the existing PLC filtering scheme mostly adopts a single filter scheme and can not obtain high-quality filtering in a complex interference environment.
The filtering method of the power line communication carrier provided by the first aspect of the invention comprises the following steps:
in response to receiving a signal filtering request, determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal;
Performing filtering operation by adopting the first original signal, and determining a first filtering score corresponding to first filtering data;
inputting the second original signal into a preset filtering neural network model, and determining a second filtering score corresponding to second filtering data;
comparing the first filtered score to the second filtered score;
outputting the first filtering data if the first filtering score is greater than the second filtering score;
and outputting the second filtering data if the first filtering score is smaller than or equal to the second filtering score.
Optionally, the step of performing filtering operation by using the first original signal to determine a first filtering score corresponding to the first filtering data includes:
the first original signal is input into a wavelet transform filter for filtering, and corresponding first filtering data are generated;
inputting the first filtering data into a preset decoder for decoding to determine a corresponding first data packet;
calculating a first checksum of the first data packet;
comparing the first checksum with an associated preset original checksum;
if the first check is consistent with the preset original check sum, the first data packet is determined to be a correct packet;
If the first check is inconsistent with the preset original checksum, determining the first data packet as an error packet;
and respectively counting the total number of the correct packets and the error packets, and generating corresponding first filtering scores by combining a preset evaluation function.
Optionally, the step of filtering with the first original signal input wavelet transform filter to generate corresponding first filtered data includes:
the first original signal is input into a wavelet transform filter for filtering, so that wavelet filtered signal data are generated;
performing image preprocessing on the wavelet filtering signal data to generate a corresponding time-frequency diagram;
inputting a preset interference signal identification model by adopting the time-frequency diagram, and determining a signal type corresponding to the wavelet filtering signal data;
and selecting a corresponding filter according to the signal type to filter the wavelet filtering signal data to generate corresponding first filtering data.
Optionally, the step of determining a second filtering score corresponding to the second filtering data by using the second original signal input preset filtering neural network model includes:
inputting a preset filtering neural network model by adopting the second original signal, and outputting corresponding second filtering data;
Inputting the second filtered data into a preset decoder for decoding to determine a corresponding second data packet;
calculating a second checksum of the second data packet;
comparing the second checksum with an associated preset original checksum;
if the second check sum is consistent with the preset original check sum, judging the second data packet as a correct packet;
if the second check sum is inconsistent with the preset original check sum, judging the second data packet as an error packet;
and respectively counting the total number of the correct packets and the error packets, and generating corresponding second filtering scores by combining a preset evaluation function.
Optionally, the preset evaluation function is specifically:
；
；
；
in the method, in the process of the invention,representing a filtered score per unit time, wherein the filtered score comprises the first filtered score per unit time and the second filtered score per unit time, < >>Indicating an integrity score per unit time,/o>Indicating error packet distribution score per unit time, +.>Indicating the total number of correct packets per unit time, +.>Representing the total number of error packets per unit time, +.>Indicating the moment in time at which the i-th erroneous packet is located per unit time,/or->Indicating the time at which the (i+1) th error packet is located in a unit time,/day >Representing a unit time.
Optionally, after the step of outputting the second filtered data if the first filtered score is less than or equal to the second filtered score, the method further includes:
taking the second filtering score as a model training standard value;
inputting a preset test signal sample set into the preset filter neural network model for model training, and generating corresponding test filter scores according to test results;
comparing the test filtering score with the model training standard value;
if the test filtering score is larger than the model training standard value, stopping training;
if the test filtering score is smaller than or equal to the model training standard value, adjusting network parameters of the preset filtering neural network model according to a preset gradient;
and skipping and executing the step of inputting the preset test signal sample set into the preset filter neural network model to perform model training and generating a corresponding test filter score according to a test result until the test filter score is greater than the model training standard value, and optimizing the preset filter neural network model.
A second aspect of the present invention provides a filtering system for a power line communication carrier, including:
The response module is used for responding to the received signal filtering request and determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal;
the first filtering score module is used for performing filtering operation by adopting the first original signal and determining a first filtering score corresponding to the first filtering data;
the second filtering score module is used for inputting a preset filtering neural network model by adopting the second original signal and determining a second filtering score corresponding to second filtering data;
a filter score comparison module for comparing the first filter score with the second filter score;
the first filtering data output module is used for outputting the first filtering data if the first filtering score is larger than the second filtering score;
and the second filtering data output module is used for outputting the second filtering data if the first filtering score is smaller than or equal to the second filtering score.
Optionally, the first filtering score module includes:
the first filtering data sub-module is used for inputting the first original signal into a wavelet transform filter for filtering to generate corresponding first filtering data;
The first data packet submodule is used for inputting the first filtering data into a preset decoder for decoding to determine a corresponding first data packet;
a first checksum sub-module, configured to calculate a first checksum of the first data packet;
the first checksum comparison sub-module is used for comparing the first checksum with the associated preset original checksum;
a first judging sub-module, configured to judge the first data packet as a correct packet if the first check is consistent with the preset original checksum;
the second judging sub-module is used for judging the first data packet as an error packet if the first check is inconsistent with the preset original checksum;
and the first statistics sub-module is used for respectively counting the total number of the correct packets and the error packets and generating corresponding first filtering scores by combining a preset evaluation function.
An electronic device according to a third aspect of the present invention includes a memory and a processor, where the memory stores a computer program, and the computer program when executed by the processor causes the processor to execute the steps of the filtering method of the power line communication carrier according to any one of the above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed, implements a method of filtering a power line communication carrier as described in any one of the above.
From the above technical scheme, the invention has the following advantages:
in response to receiving a signal filtering request, determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal, performing filtering operation by adopting the first original signal, determining a first filtering score corresponding to the first filtering data, inputting a preset filtering neural network model by adopting the second original signal, determining a second filtering score corresponding to the second filtering data, comparing the first filtering score with the second filtering score, outputting the first filtering data if the first filtering score is larger than the second filtering score, and outputting the second filtering data if the first filtering score is smaller than or equal to the second filtering score; the method solves the technical problem that the existing PLC filtering scheme adopts a single filter scheme mostly, and can not obtain high-quality filtering in a complex interference environment; different filters are adopted for filtering aiming at different interference signals, and the accuracy of signal restoration is improved; meanwhile, the filtering quality score of the neural network is continuously improved through continuous training, and the filtering quality score exceeds the filtering of fixed filters in different situations, so that the high-quality filtering of the neural network suitable for the local interference situation is trained; and the original signals are subjected to double-path shunt treatment, so that the adaptability to the complex power grid environment is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart of a filtering method of a power line communication carrier according to an embodiment of the present invention;
fig. 2 is a flowchart of a filtering method of a power line communication carrier according to a second embodiment of the present invention;
fig. 3 is another schematic diagram of a filtering method of a power line communication carrier according to a second embodiment of the present invention;
fig. 4 is a schematic diagram of a decoder front-end according to a second embodiment of the present invention;
fig. 5 is a block diagram of a filtering system for a power line communication carrier according to a third embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a filtering method, a system, equipment and a medium of a power line communication carrier, which are used for solving the technical problem that the existing PLC filtering scheme mostly adopts a single filter scheme and cannot obtain high-quality filtering in a complex interference environment.
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a filtering method of a power line communication carrier according to an embodiment of the invention.
The invention provides a filtering method of a power line communication carrier, which comprises the following steps:
step 101, in response to receiving a signal filtering request, determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal.
Signal filtering request refers to when request information for filtering an original signal is received.
In the embodiment of the invention, in response to receiving the signal filtering request, the original signal data carried by the signal filtering request is determined.
It should be noted that the original signal data includes a first original signal and a second original signal, where the first original signal and the second original signal are two-way filtering operations are performed on the original signal data carried by the signal filtering request, the first original signal is subjected to classified filtering, and the second original signal enters a preset filtering neural network model for filtering.
Step 102, performing filtering operation by using the first original signal, and determining that the first filtering data corresponds to the first filtering score.
The filtering operation refers to sequentially performing a wavelet transform filter, decoding, calculating and checking data packets, and calculating a first filtering score.
In the embodiment of the invention, a first original signal is adopted to sequentially perform wavelet transform filter, decoding, calculation and verification of data packets and calculation of a first filtering score, so that the first filtering score corresponding to the first filtering data is determined.
And step 103, inputting a second original signal into a preset filtering neural network model, and determining a second filtering score corresponding to second filtering data.
The preset filtering neural network model refers to a preset neural network filter, and is an untrained neural network filter for filtering the second original signal.
It should be noted that the predetermined filtering neural network model may be an IIR (Infinite IMP23012908ulse Response recursive filter) or an FIR (finish IMP23012908ulse Response non-recursive filter), and neither an IR (RNN) filter nor an FIR (CNN) filter may be regarded as a simple neural network, which is not limited in this embodiment.
In the embodiment of the invention, a second original signal is input into a preset filter neural network model, corresponding second filter data is output, and then decoding, calculating and checking data packets and calculating second filter scores are carried out, so that the second filter scores corresponding to the second filter data are determined.
Step 104, comparing the first filtering score with the second filtering score.
In the embodiment of the invention, the calculated first filtering score and the second filtering score are input into a comparator for comparison, so that the output filtering data is determined.
Step 105, if the first filtering score is greater than the second filtering score, outputting the first filtering data.
In the embodiment of the invention, if the first filtering score is greater than the second filtering score, the first filtering data is output.
And 106, outputting the second filtering data if the first filtering score is smaller than or equal to the second filtering score.
In the embodiment of the invention, if the first filtering score is smaller than or equal to the second filtering score, outputting second filtering data.
In the invention, original signal data corresponding to a signal filtering request is determined in response to the received signal filtering request, wherein the original signal data comprises a first original signal and a second original signal, the first original signal is adopted for filtering operation, a first filtering score corresponding to the first filtering data is determined, a second original signal is adopted for inputting a preset filtering neural network model, a second filtering score corresponding to the second filtering data is determined, the first filtering score and the second filtering score are compared, if the first filtering score is larger than the second filtering score, the first filtering data is output, and if the first filtering score is smaller than or equal to the second filtering score, the second filtering data is output; the method solves the technical problem that the existing PLC filtering scheme adopts a single filter scheme mostly, and can not obtain high-quality filtering in a complex interference environment; different filters are adopted for filtering aiming at different interference signals, and the accuracy of signal restoration is improved; meanwhile, the filtering quality score of the neural network is continuously improved through continuous training, and the filtering quality score exceeds the filtering of fixed filters in different situations, so that the high-quality filtering of the neural network suitable for the local interference situation is trained; and the original signals are subjected to double-path shunt treatment, so that the adaptability to the complex power grid environment is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating a filtering method of a power line communication carrier according to a second embodiment of the present invention.
The invention provides a filtering method of a power line communication carrier, which comprises the following steps:
in step 201, in response to receiving the signal filtering request, original signal data corresponding to the signal filtering request is determined, where the original signal data includes a first original signal and a second original signal.
In the embodiment of the present invention, the implementation process of step 201 is similar to that of step 101, and will not be repeated here.
Step 202, a first original signal is input into a wavelet transform filter for filtering, and corresponding first filtering data is generated.
Further, step 202 may comprise the sub-steps of:
s11, a first original signal is input into a wavelet transform filter for filtering, and wavelet filtering signal data are generated.
The wavelet transform filter refers to a Gabor wavelet transform filter, wherein the principle of the wavelet transform filter is as follows: the received first original signal is decomposed by wavelet transformation to obtain the bandwidth and signal strength of each sub-band. The calculation formula is as follows:
；
in the method, in the process of the invention,for wavelet coefficients, the carrier signal is indicated as +. >Under the scale, taking b as a central point, taking a as a wavelet transformation result of the scale, and +.>For the original power line carrier signal, < > is->Is a wavelet basis function.
In the embodiment of the invention, a first original signal is input into a wavelet transform filter for filtering, and the filtered wavelet filtered signal data enters an interference judgment device, wherein the interference judgment device is equivalent to a preset interference signal identification model and is used for carrying out type identification on an interference first original signal.
S12, performing image preprocessing on the wavelet filtering signal data to generate a corresponding time-frequency diagram.
Further, S12 may comprise the sub-steps of:
s121, performing short-time Fourier transform on wavelet filtered signal data to generate a time-frequency gray scale image;
s122, performing noise reduction operation on the time-frequency gray image to generate a noise-reduction time-frequency image;
s123, binarizing the noise reduction time-frequency image by adopting a preset binarization threshold value to obtain a binarized image;
s124, corroding and expanding the binarized image to obtain a corresponding time-frequency diagram.
Image corrosion, after the image is corroded, noise is removed, but the image is compressed;
the image is expanded, and the corroded image is expanded, so that noise can be removed, and the original shape can be maintained.
In the embodiment of the invention, a spectrum function spline is called under the sampling frequency, the wavelet filtering signal data is subjected to image preprocessing, the input signal is subjected to STFT processing to obtain two-dimensional array data containing time and frequency sequences, a time-frequency matrix is obtained by processing, and a signal time spectrogram is drawn.
S13, inputting a preset interference signal identification model by adopting a time-frequency diagram, and determining the signal type corresponding to the wavelet filtering signal data.
In a specific implementation, the preset interference signal recognition model is an improved recognition model, and is a recognition neural network model constructed by coupling a backbone network, a fusion network and a decoupling head prediction network.
The backbone network consists of a trick layer and a MobileNet V3 network, wherein the trick layer firstly carries out slicing operation on gray time-frequency images with the original input size of 640 multiplied by 640, after splicing, a convolution operation is carried out, and finally 320 multiplied by 320 characteristic images are generated and input into the MobileNet V3 network for characteristic extraction, so that the characteristic images of the 3-layer to-be-input characteristic fusion network are obtained, and the sizes of the characteristic images are 80 multiplied by 80, 40 multiplied by 40 and 20 multiplied by 20 respectively. The MobileNet V3 is a lighter-weight network which is built on the basis of the MobileNet V1, and the MobileNet V3 can greatly improve the accuracy and the speed of the whole network.
The fusion network utilizes a feature pyramid FPN+PAN structure to perform feature fusion of strong semantics and strong positioning on a 3-layer feature map, wherein the FPN structure transmits deep semantic features to a shallow layer in a deep-to-shallow mode to enhance semantic expression on multiple scales, and the PAN structure transmits positioning information of the shallow layer to the deep layer to enhance positioning capability on multiple scales.
The decoupling head prediction network adopts a decoupling head structure, the input fused feature diagram is divided into two paths of convolution features in parallel, classification tasks and regression tasks are respectively processed, the result is predicted in an anchor-free mode, preliminary screening is completed, and the result is subjected to fine screening by utilizing a SimOTA algorithm to obtain a final prediction result.
The time-frequency image data set is used as the input of a preset interference signal identification model, and corresponding characteristics are extracted through the preset interference signal identification model.
The method comprises the steps of adopting a frequency domain image of a sample interference signal and preprocessing the frequency domain image to construct a frequency domain image sample set; wherein the pretreatment includes short time fourier transform, noise reduction operation, binarization, corrosion and expansion. And inputting a frequency domain image sample set into a preset initial neural network model for training, so as to generate a preset interference signal identification model.
In the embodiment of the invention, a time-frequency diagram is adopted to input a preset interference signal identification model, and the signal type corresponding to the wavelet filtering signal data is determined.
S14, selecting a corresponding filter according to the signal type to filter the wavelet filtering signal data, and generating corresponding first filtering data.
In the embodiment of the invention, a corresponding filter is selected according to the signal type to filter the wavelet filtered signal data, so as to generate corresponding first filtered data.
According to the embodiment of the invention, 3 types of interference signals are taken as examples, and corresponding signal types can be output according to a preset interference signal identification model, wherein the signal types can comprise strong interference signals, specific distance selective interference, frequency selective interference and the like, and if the signal types belong to the strong interference signals, the signal types are filtered by a frequency domain filter; if the interference is interference of a specific distance, a distance selective interference filter is entered; if the interference is frequency selective interference, entering a wavelet packet transformation filter; if multiple signal types occur simultaneously, the filters corresponding to the multiple signal types are used for serial filtering.
And filtering the received strong interference signal by frequency domain filtering, wherein only the main components of the signal are reserved, so that the influence of the interference signal on the original signal is reduced. Frequency domain filter formula the formula of the frequency domain filter can be expressed as:
；
in the method, in the process of the invention,representing the frequency response of a frequency domain filter, wherein the frequency response of the frequency domain filter may achieve a specific filtering effect by some window function or filter function,/or->Representing the input signal>Representing the output signal.
For some specific distance selective interferences, a distance selective filter is adopted for processing, so that the influence of interference signals on a receiving end is reduced. Distance selective filter formula the distance formula of the selective filter can be expressed as:
；
in the method, in the process of the invention,filter center coordinates,/->Representing the filter center point, < >>Representing the euclidean distance from the current pixel point.
For frequency selective interference, a wavelet packet transformation technology is adopted for analysis and processing at a receiving end. Wavelet packet transform technique the formula wavelet packet transform is a further extension of the wavelet transform. The mathematical formula is as follows:
is provided withFor the original signal +.>For time (I)>And->For the scale and translation parameters in the wavelet packet basis function, the wavelet packet transform coefficients are:
；
In the method, in the process of the invention,and->Representing scale and translation parameters, respectively, < >>Representing wavelet packet basis function, < ->Representing a discrete time variable.
The wavelet packet basis function has the expression:
；
in the method, in the process of the invention,representing the wavelet basis functions.
And 203, inputting the first filtered data into a preset decoder for decoding, and determining a corresponding first data packet.
As shown in fig. 4, the conventional decoder is usually at a rear position, while the present invention adopts the front position of the decoder, the comparison result of the comparator returns to the preset filtering neural network model training, and the comparison dominant data is output, wherein the data quality evaluation is performed on the original signals after two paths of filtering, and the same decoder and the preset evaluation function are arranged at the output ends of the two paths. Wherein the first filtered score evaluation is consistent with the second filtered score evaluation.
The decoder may implement the retrieval of data from the physical layer by decoding and reassembling the data packets. The specific operation flow is as follows:
receiving a data packet: the decoder receives the first data packet associated with the classified and filtered first filtering data from the physical layer and receives the first data packet through the receiving port.
Decoding the data packet: the decoder decodes the received first data packet and converts the encoded first data packet into an original data packet.
Reorganizing the data packet: by concatenating the first plurality of data packets, the decoder reassembles the original data packets for subsequent processing and transmission.
Outputting decoded data: after decoding and reassembly, the decoder outputs the decoded data packet to an upper protocol layer, such as an application layer, for subsequent data processing and transmission.
The decoder functions at the physical layer to convert the bit stream into data packets, which are typically embedded in a network card. When the network card receives a data packet, the data packet is transmitted to the operating system, and the operating system decodes the data packet through a protocol module of the network protocol stack.
In particular, the process of decoding a packet from the physical layer by a decoder can be divided into the following steps:
the bit stream received by the physical layer is divided into data blocks, which are transmitted in frames, each frame containing data and some control information.
By means of the control information of the frame, it is determined to which network layer protocol the data in the frame belongs, e.g. IP.
Extracting an IP header, and analyzing information such as a source IP address, a target IP address, a protocol type, the length of a data part and the like.
Depending on the protocol type, the data portion is passed to a decoder of the corresponding protocol for decoding, e.g. the TCP or UDP protocol.
In the embodiment of the invention, the first filtering data is input into a preset decoder for decoding, and the corresponding first data packet is determined.
Step 204, calculating a first checksum of the first data packet.
Step 205, comparing the first checksum with an associated preset original checksum.
It should be noted that, the preset original checksum refers to an original checksum of an original data packet associated with the first original signal, and is used for judging whether the filtered first data packet is a correct packet or an error packet.
Step 206, if the first check is consistent with the preset original checksum, the first data packet is determined to be a correct packet.
Step 207, if the first check is inconsistent with the preset original checksum, the first data packet is determined to be an error packet.
Step 208, counting the total number of the correct packets and the error packets respectively, and generating corresponding first filtering scores by combining a preset evaluation function.
In the embodiment of the present invention, in step 204-step 208, the calculation of the first filtering score is required to count the total number of correct packets and error packets, and the decoding of the first data packet is required, and the integrity check of the data packet refers to the checking of the data packet in the IP protocol, so as to confirm whether the data packet is correct or not in the transmission process. The IP protocol uses a checksum to ensure the integrity of the first data packet. When transmitting a data packet, the sender calculates a checksum of each byte in the first data packet and sends the result together with the first data packet to the receiver. The receiving side calculates the checksum of each byte in the data packet after receiving the first data packet, and then compares the result with the checksum sent by the sending side. If the two checksums are the same, the data packet is considered to be valid, and the first data packet is judged to be a correct packet; if the two checksums are different, the first data packet is considered to be damaged or tampered with and discarded, and the first data packet is determined to be an erroneous packet. And respectively counting the total number of the correct packets and the error packets, and generating corresponding first filtering scores by combining a preset evaluation function.
It should be noted that, the method of calculation and verification is that all characters in the file are read as a whole character string. Each character is converted into decimal ASCI code. Since two characters are combined into an integer of 16 bits, here i add the high order and the high order, and add the low order, if the number of characters is odd, then the last character is further appended with a byte of 0 to make an even number. The lower added carry and the higher added carry are then processed, where the higher carry is processed in a round-robin fashion, as adding the higher carry to the lower bit may also produce a carry. The result of the processing is decimal, and the result is converted into hexadecimal.
That is, the checksum calculation is obtained by summing each 16-bit word in the packet and bit-wise complementing (inverting) the result with 16 1's. The purpose of this is to ensure that when calculating the checksum of the data packet, even if a bit in the data packet is inverted, the checksum is changed, thereby eliminating erroneous decisions.
Packet parsing refers to analyzing the contents of a packet with an IP header. Generally, the structure of the data packet is such that:
Source IP address (32 bits) |destination IP address (32 bits) |protocol version (4 bits) |header length (4 bits) |differentiated services (8 bits) |total length (16 bits) | identifies (16 bits) |flag (3 bits) |slice offset (13 bits) |time-to-live (8 bits) |protocol (8 bits) |checksum (16 bits) |source address (32 bits) |destination address (32 bits) |optional and fill (optional)
Within these fields, a source IP address and a destination IP address are necessary, which are used to determine the transmission and reception locations of the data packets. The protocol version and header length then specify the IP protocol version and header fixed length used for this packet. Differentiated services are an 8-bit field that specifies the type of service, such as latency, throughput, and reliability, of a packet.
The following is the total length and identification, which define the size and uniqueness of the data packet. The flags and slice offsets are used to divide the large packet into multiple segments to accommodate different network transmissions. The time-to-live field defines the lifetime of the packet, which is discarded when it becomes 0. The protocol field describes an upper layer protocol used in the data packet, such as TCP or UDP. The last field is a checksum for checking whether the packet is corrupted or tampered with.
And 209, inputting a second original signal into a preset filtering neural network model, and determining a second filtering score corresponding to the second filtering data.
Further, step 209 may include the sub-steps of:
s21, inputting a second original signal into a preset filtering neural network model, and outputting corresponding second filtering data.
In the embodiment of the invention, a second original signal is input into a preset filtering neural network model, and corresponding second filtering data is output.
S22, inputting second filtering data into a preset decoder for decoding, and determining a corresponding second data packet.
S23, calculating a second checksum of the second data packet.
S24, comparing the second checksum with the associated preset original checksum.
S25, if the second check is consistent with the preset original check sum, judging the second data packet as a correct packet.
S26, if the second check is inconsistent with the preset original check sum, judging the second data packet as an error packet.
S27, counting the total number of the correct packets and the error packets respectively, and generating corresponding second filtering scores by combining a preset evaluation function.
In the embodiment of the present invention, the specific implementation process of S22-S27 is similar to steps 204-208, and will not be described herein.
Further, the preset evaluation function in steps 208 and S27 is specifically:
；
；
；
in the method, in the process of the invention,representing the filter score per unit time, wherein the filter score comprises a first filter score per unit time and a second filter score per unit time, < >>Indicating an integrity score per unit time,/o>Indicating error packet distribution score per unit time, +.>Indicating the total number of correct packets per unit time, +.>Representing the total number of error packets per unit time, +.>Indicating the moment in time at which the i-th erroneous packet is located per unit time,/or->Indicating the time at which the (i+1) th error packet is located in a unit time,/day>Representing a unit time.
The first filtering score and the second filtering score are obtained through calculation of a preset evaluation function.
Unit time refers to the total time measured from the time the original signal was sent to the time the decoder was finished decoding.
Because the original signal is continuously sent out according to the preset interval, belongs to the form of data stream, filtering is continuously carried out, and the error interval time of two adjacent error packets in unit time is calculated by acquiring the time of each error packet in unit time, so as to obtain the error packet distribution score.
Step 210, comparing the first filtering score with the second filtering score.
In the embodiment of the present invention, the implementation process of step 210 is similar to that of step 104, and will not be repeated here.
Step 211, if the first filtering score is greater than the second filtering score, outputting the first filtering data.
In the embodiment of the present invention, the implementation process of step 211 is similar to that of step 105, and will not be repeated here.
Step 212, if the first filtering score is less than or equal to the second filtering score, outputting the second filtering data.
In the embodiment of the present invention, the implementation process of step 212 is similar to that of step 106, and will not be repeated here.
Further, after step 212, the method further includes:
and 213, taking the second filtering score as a model training standard value.
In the embodiment of the invention, the second filtering score is used as a model training standard value, namely, the second filtering score is used as a preset filtering neural network model training index.
And 214, inputting a preset filtering neural network model by using a preset test signal sample set to perform model training, and generating a corresponding test filtering score according to a test result.
In the embodiment of the present invention, the preset filtering neural network model may be obtained by modifying and training any one of the convolutional neural network CNN (Convolutional Neural Networks), the regional convolutional neural network R-CNN (Region with CNN Feature), the fast R-CNN (Faster Region with CNN Feature), the Mask R-CNN (Mask Region with CNN Feature), and the like, which is not limited in this embodiment.
And step 215, comparing the test filtering score with a model training standard value.
And step 216, if the test filtering score is greater than the model training standard value, stopping training.
And step 217, if the test filtering score is smaller than or equal to the model training standard value, adjusting network parameters of a preset filtering neural network model according to a preset gradient.
And step 218, jumping to execute the step of inputting a preset test signal sample set into a preset filter neural network model to perform model training and generating a corresponding test filter score according to a test result until the test filter score is greater than a model training standard value, and optimizing the preset filter neural network model.
In the invention, original signal data corresponding to a signal filtering request is determined in response to the received signal filtering request, wherein the original signal data comprises a first original signal and a second original signal, the first original signal is adopted for filtering operation, a first filtering score corresponding to the first filtering data is determined, a second original signal is adopted for inputting a preset filtering neural network model, a second filtering score corresponding to the second filtering data is determined, the first filtering score and the second filtering score are compared, if the first filtering score is larger than the second filtering score, the first filtering data is output, and if the first filtering score is smaller than or equal to the second filtering score, the second filtering data is output; the method solves the technical problem that the existing PLC filtering scheme adopts a single filter scheme mostly, and can not obtain high-quality filtering in a complex interference environment; different filters are adopted for filtering aiming at different interference signals, and the accuracy of signal restoration is improved; meanwhile, the filtering quality score of the neural network is continuously improved through continuous training, and the filtering quality score exceeds the filtering of fixed filters in different situations, so that the high-quality filtering of the neural network suitable for the local interference situation is trained; and the original signals are subjected to double-path shunt treatment, so that the adaptability to the complex power grid environment is improved.
Referring to fig. 5, fig. 5 is a block diagram of a filtering system for a power line communication carrier according to a third embodiment of the present invention.
The invention provides a filtering system of a power line communication carrier, which comprises:
a response module 301, configured to determine, in response to receiving a signal filtering request, original signal data corresponding to the signal filtering request, where the original signal data includes a first original signal and a second original signal;
the first filtering score module 302 is configured to perform a filtering operation by using the first original signal, and determine that the first filtering data corresponds to the first filtering score;
the second filtering score module 303 is configured to input a preset filtering neural network model to a second original signal, and determine a second filtering score corresponding to the second filtering data;
a filter score comparison module 304 for comparing the first filter score with the second filter score;
a first filtered data output module 305, configured to output first filtered data if the first filtered score is greater than the second filtered score;
the second filtered data output module 306 is configured to output the second filtered data if the first filtered score is less than or equal to the second filtered score.
Further, the first filter score module 302 includes:
The first filtering data sub-module is used for inputting a first original signal into the wavelet transform filter for filtering to generate corresponding first filtering data;
the first data packet submodule is used for inputting first filtering data into a preset decoder for decoding to determine a corresponding first data packet;
the first checksum sub-module is used for calculating a first checksum of the first data packet;
the first checksum comparison sub-module is used for comparing the first checksum with the associated preset original checksum;
the first judging sub-module is used for judging the first data packet as a correct packet if the first check is consistent with the preset original check sum;
the second judging sub-module is used for judging the first data packet as an error packet if the first check is inconsistent with the preset original check sum;
and the first statistics sub-module is used for respectively counting the total number of the correct packets and the error packets and generating corresponding first filtering scores by combining a preset evaluation function.
Further, the first filtered data sub-module includes:
the wavelet filtering signal data unit is used for inputting a first original signal into the wavelet transformation filter for filtering to generate wavelet filtering signal data;
the time-frequency diagram unit is used for carrying out image preprocessing on the wavelet filtering signal data to generate a corresponding time-frequency diagram;
The signal type unit is used for inputting a preset interference signal identification model by using a time-frequency diagram and determining the signal type corresponding to the wavelet filtering signal data;
the filter selecting unit is used for selecting a corresponding filter according to the signal type to filter the wavelet filtering signal data, and generating corresponding first filtering data.
Further, the second filter score module 303 includes:
the second filtering data sub-module is used for inputting a preset filtering neural network model by adopting a second original signal and outputting corresponding second filtering data;
the second data packet submodule is used for inputting second filtering data into a preset decoder for decoding, and determining a corresponding second data packet;
a second checksum sub-module for calculating a second checksum of the second data packet;
the second checksum comparison sub-module is used for comparing the second checksum with the associated preset original checksum;
the third judging sub-module is used for judging the second data packet as a correct packet if the second check is consistent with the preset original check sum;
a fourth determining sub-module, configured to determine the second data packet as an error packet if the second checksum is inconsistent with the preset original checksum;
and the second statistics sub-module is used for respectively counting the total number of the correct packets and the error packets and generating corresponding second filtering scores by combining a preset evaluation function.
Further, the preset evaluation function specifically includes:
；
；
；
in the method, in the process of the invention,representing the filter score per unit time, wherein the filter score comprises a first filter score per unit time and a second filter score per unit time, < >>Indicating an integrity score per unit time,/o>Indicating the error packet distribution score per unit time,indicating the total number of correct packets per unit time, +.>Representing the total number of error packets per unit time, +.>Indicating the moment in time at which the i-th erroneous packet is located per unit time,/or->Indicating the time at which the (i+1) th error packet is located in a unit time,/day>Representing a unit time.
Further, the method further comprises the following steps:
the model training standard value module is used for taking the second filtering score as a model training standard value;
the test filtering score module is used for inputting a preset test signal sample set into a preset filter neural network model for model training, and generating a corresponding test filtering score according to a test result;
the model score comparison module is used for comparing the test filtering score with a model training standard value;
the first training module is used for stopping training if the test filtering score is larger than the model training standard value;
the second training module is used for adjusting network parameters of a preset filter neural network model according to a preset gradient if the test filter score is smaller than or equal to a model training standard value;
And the jump module is used for jumping to execute the steps of inputting a preset test signal sample set into the preset filter neural network model for model training and generating a corresponding test filter score according to a test result until the test filter score is larger than a model training standard value, and optimizing the preset filter neural network model.
In the invention, original signal data corresponding to a signal filtering request is determined in response to the received signal filtering request, wherein the original signal data comprises a first original signal and a second original signal, the first original signal is adopted for filtering operation, a first filtering score corresponding to the first filtering data is determined, a second original signal is adopted for inputting a preset filtering neural network model, a second filtering score corresponding to the second filtering data is determined, the first filtering score and the second filtering score are compared, if the first filtering score is larger than the second filtering score, the first filtering data is output, and if the first filtering score is smaller than or equal to the second filtering score, the second filtering data is output; the method solves the technical problem that the existing PLC filtering scheme adopts a single filter scheme mostly, and can not obtain high-quality filtering in a complex interference environment; different filters are adopted for filtering aiming at different interference signals, and the accuracy of signal restoration is improved; meanwhile, the filtering quality score of the neural network is continuously improved through continuous training, and the filtering quality score exceeds the filtering of fixed filters in different situations, so that the high-quality filtering of the neural network suitable for the local interference situation is trained; and the original signals are subjected to double-path shunt treatment, so that the adaptability to the complex power grid environment is improved.
An electronic device according to an embodiment of the present invention includes: a memory and a processor, the memory storing a computer program; the computer program, when executed by a processor, causes the processor to perform the method of filtering a power line communication carrier as in any of the embodiments described above.
The memory may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory has memory space for program code to perform any of the method steps described above. For example, the memory space for the program code may include individual program code for implementing the various steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. The program code may be compressed, for example, in a suitable form. The code, when executed by a computing processing device, causes the computing processing device to perform the steps in the method described above.
An embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed, implements a method for filtering a power line communication carrier as in any embodiment of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for filtering a power line communication carrier, comprising:
in response to receiving a signal filtering request, determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal;
performing filtering operation by adopting the first original signal, and determining a first filtering score corresponding to first filtering data;
inputting the second original signal into a preset filtering neural network model, and determining a second filtering score corresponding to second filtering data;
comparing the first filtered score to the second filtered score;
outputting the first filtering data if the first filtering score is greater than the second filtering score;
Outputting the second filtered data if the first filtered score is less than or equal to the second filtered score;
the step of performing filtering operation by using the first original signal to determine a first filtering score corresponding to the first filtering data includes:
the first original signal is input into a wavelet transform filter for filtering, and corresponding first filtering data are generated;
inputting the first filtering data into a preset decoder for decoding to determine a corresponding first data packet;
calculating a first checksum of the first data packet;
comparing the first checksum with an associated preset original checksum;
if the first checksum is consistent with the preset original checksum, the first data packet is determined to be a correct packet;
if the first checksum is inconsistent with the preset original checksum, the first data packet is determined to be an error packet;
and respectively counting the total number of the correct packets and the error packets, and generating corresponding first filtering scores by combining a preset evaluation function.
2. The method of filtering a power line communication carrier according to claim 1, wherein the step of filtering with the first original signal input wavelet transform filter to generate corresponding first filtered data includes:
The first original signal is input into a wavelet transform filter for filtering, so that wavelet filtered signal data are generated;
performing image preprocessing on the wavelet filtering signal data to generate a corresponding time-frequency diagram;
inputting a preset interference signal identification model by adopting the time-frequency diagram, and determining a signal type corresponding to the wavelet filtering signal data;
and selecting a corresponding filter according to the signal type to filter the wavelet filtering signal data to generate corresponding first filtering data.
3. The method of filtering a power line communication carrier according to claim 1, wherein the step of determining a second filtering score corresponding to second filtering data using the second raw signal input preset filtering neural network model includes:
inputting a preset filtering neural network model by adopting the second original signal, and outputting corresponding second filtering data;
inputting the second filtered data into a preset decoder for decoding to determine a corresponding second data packet;
calculating a second checksum of the second data packet;
comparing the second checksum with an associated preset original checksum;
if the second checksum is consistent with the preset original checksum, judging the second data packet as a correct packet;
If the second checksum is inconsistent with the preset original checksum, the second data packet is judged to be an error packet;
and respectively counting the total number of the correct packets and the error packets, and generating corresponding second filtering scores by combining a preset evaluation function.
4. A method for filtering a power line communication carrier according to claim 1 or 3, wherein the preset evaluation function is specifically:
；
；
；
in the method, in the process of the invention,representing a filtered score per unit time, wherein the filtered score comprises the first filtered score per unit time and the second filtered score per unit time, < >>Indicating an integrity score per unit time,/o>Indicating error packet distribution score per unit time, +.>Indicating the total number of correct packets per unit time, +.>Representing the total number of error packets per unit time, +.>Indicating the moment in time at which the i-th erroneous packet is located per unit time,/or->Representing the i+1th error packet in a unit timeTime of day at->Representing a unit time.
5. The method according to claim 1, wherein after the step of outputting the second filter data if the first filter score is less than or equal to the second filter score, further comprising:
Taking the second filtering score as a model training standard value;
inputting a preset test signal sample set into the preset filter neural network model for model training, and generating corresponding test filter scores according to test results;
comparing the test filtering score with the model training standard value;
if the test filtering score is larger than the model training standard value, stopping training;
if the test filtering score is smaller than or equal to the model training standard value, adjusting network parameters of the preset filtering neural network model according to a preset gradient;
and skipping and executing the step of inputting the preset test signal sample set into the preset filter neural network model to perform model training and generating a corresponding test filter score according to a test result until the test filter score is greater than the model training standard value, and optimizing the preset filter neural network model.
6. A power line communication carrier filtering system, comprising:
the response module is used for responding to the received signal filtering request and determining original signal data corresponding to the signal filtering request, wherein the original signal data comprises a first original signal and a second original signal;
The first filtering score module is used for performing filtering operation by adopting the first original signal and determining a first filtering score corresponding to the first filtering data;
the second filtering score module is used for inputting a preset filtering neural network model by adopting the second original signal and determining a second filtering score corresponding to second filtering data;
a filter score comparison module for comparing the first filter score with the second filter score;
the first filtering data output module is used for outputting the first filtering data if the first filtering score is larger than the second filtering score;
the second filtering data output module is used for outputting the second filtering data if the first filtering score is smaller than or equal to the second filtering score;
the first filter score module includes:
the first filtering data sub-module is used for inputting the first original signal into a wavelet transform filter for filtering to generate corresponding first filtering data;
the first data packet submodule is used for inputting the first filtering data into a preset decoder for decoding to determine a corresponding first data packet;
a first checksum sub-module, configured to calculate a first checksum of the first data packet;
The first checksum comparison sub-module is used for comparing the first checksum with the associated preset original checksum;
the first judging sub-module is used for judging the first data packet as a correct packet if the first checksum is consistent with the preset original checksum;
the second judging sub-module is used for judging the first data packet as an error packet if the first checksum is inconsistent with the preset original checksum;
and the first statistics sub-module is used for respectively counting the total number of the correct packets and the error packets and generating corresponding first filtering scores by combining a preset evaluation function.
7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method for filtering a power line communication carrier according to any one of claims 1-5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed, implements the method of filtering a power line communication carrier according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310814914.0A CN116527084B (en) | 2023-07-05 | 2023-07-05 | Filtering method, system, equipment and medium for power line communication carrier |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310814914.0A CN116527084B (en) | 2023-07-05 | 2023-07-05 | Filtering method, system, equipment and medium for power line communication carrier |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116527084A CN116527084A (en) | 2023-08-01 |
| CN116527084B true CN116527084B (en) | 2023-12-05 |
Family
ID=87398046
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310814914.0A Active CN116527084B (en) | 2023-07-05 | 2023-07-05 | Filtering method, system, equipment and medium for power line communication carrier |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116527084B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1854699A (en) * | 2005-04-20 | 2006-11-01 | 精拓科技股份有限公司 | Anti-noise device and method for measuring temperature |
| CN103067710A (en) * | 2012-12-28 | 2013-04-24 | 辽宁师范大学 | Distributed hyperspectral image coding and decoding method based on three-dimensional wavelet transform |
| CN105629060A (en) * | 2015-12-24 | 2016-06-01 | 电子科技大学 | Grid frequency measurement method and device based on optimal baseband filtering |
| CN112162144A (en) * | 2020-08-19 | 2021-01-01 | 国网江西省电力有限公司供电服务管理中心 | Power grid frequency rapid measurement method and device based on convolution gain |
-
2023
- 2023-07-05 CN CN202310814914.0A patent/CN116527084B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1854699A (en) * | 2005-04-20 | 2006-11-01 | 精拓科技股份有限公司 | Anti-noise device and method for measuring temperature |
| CN103067710A (en) * | 2012-12-28 | 2013-04-24 | 辽宁师范大学 | Distributed hyperspectral image coding and decoding method based on three-dimensional wavelet transform |
| CN105629060A (en) * | 2015-12-24 | 2016-06-01 | 电子科技大学 | Grid frequency measurement method and device based on optimal baseband filtering |
| CN112162144A (en) * | 2020-08-19 | 2021-01-01 | 国网江西省电力有限公司供电服务管理中心 | Power grid frequency rapid measurement method and device based on convolution gain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116527084A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111901296A (en) | Network attack behavior detection method and detection system | |
| CN114143107B (en) | Low-speed DDoS attack detection method, system and related equipment | |
| US20230326468A1 (en) | Audio processing of missing audio information | |
| CN107911254B (en) | Log transmission method and device, computing equipment and storage medium | |
| US11477308B2 (en) | Adaptive payload extraction in wireless communications involving multi-access address packets | |
| CN110691035A (en) | Method and device for determining network congestion, electronic equipment and storage medium | |
| CN116346384A (en) | Malicious encryption flow detection method based on variation self-encoder | |
| CN111355671B (en) | Network traffic classification method, medium and terminal equipment based on self-attention mechanism | |
| CN116915363A (en) | Data transmission method, device and equipment | |
| CN116527084B (en) | Filtering method, system, equipment and medium for power line communication carrier | |
| CN113300916B (en) | Data center network congestion detection system and method based on stream watermarking | |
| CN103456307A (en) | Spectrum replacement method and system for frame error hiding in audio decoder | |
| CN109756358B (en) | Sampling frequency recommendation method, device, equipment and storage medium | |
| CN106656201B (en) | Compression method based on amplitude-frequency characteristics of sampled data | |
| CN104767997A (en) | Video-oriented visual feature encoding method and device | |
| CN115333903B (en) | Synchronization head detection method, synchronization device, receiver and communication system | |
| CN113242473B (en) | Data processing method, system, data acquisition equipment and readable storage medium | |
| CN115347978A (en) | Method, device and storage medium for identifying AIS frame header data | |
| CN105915228A (en) | Adaptive mixed data lossless compression method | |
| CN110298398B (en) | Wireless protocol frame characteristic selection method based on improved mutual information | |
| CN106789895B (en) | Compressed text detection method and device | |
| CN112201271B (en) | Voice state statistical method and system based on VAD and readable storage medium | |
| CN110401813B (en) | Dynamic information network transmission mechanism | |
| CN116015310A (en) | Data lossless compression method and device | |
| CN109147795A (en) | Voice print database transmission, recognition methods, identification device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |